Zobrazeno 1 - 10
of 39
pro vyhledávání: '"CHOI, KRISTY"'
Autor:
Hwang, Jyh-Jing, Xu, Runsheng, Lin, Hubert, Hung, Wei-Chih, Ji, Jingwei, Choi, Kristy, Huang, Di, He, Tong, Covington, Paul, Sapp, Benjamin, Guo, James, Anguelov, Dragomir, Tan, Mingxing
We introduce EMMA, an End-to-end Multimodal Model for Autonomous driving. Built on a multi-modal large language model foundation, EMMA directly maps raw camera sensor data into various driving-specific outputs, including planner trajectories, percept
Externí odkaz:
http://arxiv.org/abs/2410.23262
Autor:
Hu, Yingjie, Mai, Gengchen, Cundy, Chris, Choi, Kristy, Lao, Ni, Liu, Wei, Lakhanpal, Gaurish, Zhou, Ryan Zhenqi, Joseph, Kenneth
Publikováno v:
International Journal of Geographical Information Science, 2023
Social media messages posted by people during natural disasters often contain important location descriptions, such as the locations of victims. Recent research has shown that many of these location descriptions go beyond simple place names, such as
Externí odkaz:
http://arxiv.org/abs/2310.09340
Representing probability distributions by the gradient of their density functions has proven effective in modeling a wide range of continuous data modalities. However, this representation is not applicable in discrete domains where the gradient is un
Externí odkaz:
http://arxiv.org/abs/2211.00802
Particularly in low-data regimes, an outstanding challenge in machine learning is developing principled techniques for augmenting our models with suitable priors. This is to encourage them to learn in ways that are compatible with our understanding o
Externí odkaz:
http://arxiv.org/abs/2210.12530
Normalizing flows model complex probability distributions using maps obtained by composing invertible layers. Special linear layers such as masked and 1x1 convolutions play a key role in existing architectures because they increase expressive power w
Externí odkaz:
http://arxiv.org/abs/2209.13774
Autor:
Taghanaki, Saeid Asgari, Gholami, Ali, Khani, Fereshte, Choi, Kristy, Tran, Linh, Zhang, Ran, Khani, Aliasghar
Batch normalization (BN) is a ubiquitous technique for training deep neural networks that accelerates their convergence to reach higher accuracy. However, we demonstrate that BN comes with a fundamental drawback: it incentivizes the model to rely on
Externí odkaz:
http://arxiv.org/abs/2207.01548
Density ratio estimation (DRE) is a fundamental machine learning technique for comparing two probability distributions. However, existing methods struggle in high-dimensional settings, as it is difficult to accurately compare probability distribution
Externí odkaz:
http://arxiv.org/abs/2111.11010
Density ratio estimation serves as an important technique in the unsupervised machine learning toolbox. However, such ratios are difficult to estimate for complex, high-dimensional data, particularly when the densities of interest are sufficiently di
Externí odkaz:
http://arxiv.org/abs/2107.02212
A fundamental challenge in artificial intelligence is learning useful representations of data that yield good performance on a downstream task, without overfitting to spurious input features. Extracting such task-relevant predictive information is pa
Externí odkaz:
http://arxiv.org/abs/2106.06620
Autor:
Isik, Berivan, Choi, Kristy, Zheng, Xin, Weissman, Tsachy, Ermon, Stefano, Wong, H. -S. Philip, Alaghi, Armin
Compression and efficient storage of neural network (NN) parameters is critical for applications that run on resource-constrained devices. Despite the significant progress in NN model compression, there has been considerably less investigation in the
Externí odkaz:
http://arxiv.org/abs/2102.07725